list_models_for_budgetFiltre le catalogue public selon une VRAM, une RAM optionnelle et un usage. Estimation catalogue uniquement : pas un scan, pas un benchmark, pas de tokens/s inventés.
| Name | Required | Description | Default |
|---|---|---|---|
| usage | No | polyvalent | |
| ram_gb | No | ||
| vram_gb | Yes | ||
| unified_memory | No | ||
| storage_free_gb | No |
| Name | Required | Description | Default |
|---|---|---|---|
| budget | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: it is only a catalog estimate, not a real scan or benchmark, and does not fabricate tokens/s. This goes beyond the annotations and helps the agent understand the tool's limitations and data sources.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences with no redundancy. The first sentence states the core function, and the second adds critical limitations. Every word earns its place; it is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema and annotations, the description does not need to detail return values. However, it omits explanation of two parameters (unified_memory, storage_free_gb) and does not describe how filtering works internally (e.g., exact match, inclusive, ordering). The core idea is conveyed, but gaps remain for full contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description should compensate. It mentions vram_gb (required), ram_gb (optional), and usage, but ignores unified_memory and storage_free_gb. This leaves two parameters unexplained, which is a significant gap for a tool with five parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('filtre') and resource ('catalogue public') along with key parameters (VRAM, RAM, usage). It also clarifies the tool's scope ('estimation catalogue uniquement'), which helps distinguish it from siblings that might perform real scans or benchmarks. However, it does not explicitly differentiate from specific sibling tools by name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: 'Estimation catalogue uniquement : pas un scan, pas un benchmark, pas de tokens/s inventés' tells the agent that this is for quick catalog-based filtering, not for live measurements. But it does not explicitly state when to prefer this tool over alternatives like 'check_pc_for_local_ai' or 'recommend_runtime', nor does it provide exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose (analyze, check, explain, list, etc.) and the detailed descriptions make boundaries clear. However, the difference between 'reading a shared report' (analyze_shared_report) and 'reading a shared report to list installed models' (list_installed_models_from_report) or 'reading a shared report to list benchmarks' (list_benchmark_proofs_from_report) could cause an agent to pick the wrong one. There is also some overlap between these list operations that read a report versus simply displaying a pre-generated cockpit (render_machine_cockpit).
The majority of tools follow a consistent verb_noun pattern (e.g., analyze_shared_report, explain_bottleneck, list_installed_models_from_report, recommend_runtime). Minor inconsistency exists with the use of 'geo_audit' vs 'geo_kit' vs 'ratings' and the verb tense in 'list_benchmark_proofs_from_report' and 'list_first_party_measurements' departs from a simple pattern.
15 tools is at the high end of the ideal range (3-15), but each tool appears justified given the comprehensive scope of local AI assistance (hardware checking, model lookup, benchmarking, reporting, educational/reference tools). Slightly over-stuffed but still manageable for an agent.
The surface covers a complete workflow: check hardware, lookup models, benchmark, generate cockpit, explain bottlenecks, simulate upgrades, and reference documentation. The missing piece is the lack of 'update' or 'delete' operations, but this is by design, as the entire workflow is read-only. The set seems like a complete view of all possible read-only interactions with the domain.